© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 90887
    Prev
    Next
    INDEX
    Explanations

    question-answer and technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    出版年
    -0.75
     المعيارى
    -0.74
    expandindo
    -0.68
    fromnode
    -0.63
    ++);
    -0.57
     Paglinawan
    -0.55
    TypedDataSet
    -0.55
    '}),
    -0.52
     AspNetCore
    -0.51
    🟤
    -0.49
    POSITIVE LOGITS
    HasOne
    0.56
    Datuak
    0.54
    there
    0.52
    èdia
    0.52
    ształ
    0.49
     tartalomajánló
    0.47
    rawDesc
    0.46
    Portale
    0.46
     warrants
    0.45
    soever
    0.45
    Activations Density 0.022%

    No Known Activations